© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 19710
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     다양한
    -0.12
    各种
    -0.10
     एका
    -0.10
    'ọ
    -0.10
    'etiti
    -0.10
    <|reserved_200000|>
    -0.10
     कई
    -0.10
     기타
    -0.09
     ساتھ
    -0.09
    的天天
    -0.09
    POSITIVE LOGITS
     approach
    0.23
     Approach
    0.19
     approche
    0.15
     examine
    0.14
     way
    0.14
    Appro
    0.14
     approached
    0.14
     think
    0.14
     we
    0.14
     understanding
    0.14
    Activations Density 0.010%

    No Known Activations